tuanna08go commited on
Commit
84cfc77
·
verified ·
1 Parent(s): 5614869

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c8d09284505a9d06766acc39b195c64e935de4cf65384350934da2380c8ba69
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a54b485fe58a06f47f292916d7d164dcd7871580bb83c5e68a49b8742a415b
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:379a3e58f68366de5618893c9240a44b96d894d86dc876bba0e7c1735705dcce
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4742c93f3b5c46b0ca16bfd73ac47197e95607cd612d605bd8977490cce92b6
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.02128203816442421,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 169.199,
46
  "eval_steps_per_second": 21.155,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 94056480768.0,
68
  "train_batch_size": 8,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03192305724663631,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 169.199,
46
  "eval_steps_per_second": 21.155,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.02455619788202793,
51
+ "grad_norm": 0.015912150964140892,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 11.9311,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.02455619788202793,
58
+ "eval_loss": 11.930720329284668,
59
+ "eval_runtime": 48.7641,
60
+ "eval_samples_per_second": 168.772,
61
+ "eval_steps_per_second": 21.102,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 140848398336.0,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null